Open Access Repository

Parkinson’s disease diagnosis using convolutional neural networks and figure-copying tasks

Alissa, M, Lones, MA, Cosgrove, J, Alty, JE ORCID: 0000-0002-5456-8676, Jamieson, S, Smith, SL and Vallejo, M 2021 , 'Parkinson’s disease diagnosis using convolutional neural networks and figure-copying tasks' , Neural Computing and Applications , doi: 10.1007/s00521-021-06469-7.

Full text not available from this repository.


Parkinson’s disease (PD) is a progressive neurodegenerative disorder that causes abnormal movements and an array ofother symptoms. An accurate PD diagnosis can be a challenging task as the signs and symptoms, particularly at an earlystage, can be similar to other medical conditions or the physiological changes of normal ageing. This work aims tocontribute to the PD diagnosis process by using a convolutional neural network, a type of deep neural network architecture,to differentiate between healthy controls and PD patients. Our approach focuses on discovering deviations in patient’smovements with the use of drawing tasks. In addition, this work explores which of two drawing tasks, wire cube or spiralpentagon, are more effective in the discrimination process. With 93:5% accuracy, our convolutional classifier, trained withimages of the pentagon drawing task and augmentation techniques, can be used as an objective method to discriminate PDfrom healthy controls. Our compact model has the potential to be developed into an offline real-time automated single-taskdiagnostic tool, which can be easily deployed within a clinical setting.

Item Type: Article
Authors/Creators:Alissa, M and Lones, MA and Cosgrove, J and Alty, JE and Jamieson, S and Smith, SL and Vallejo, M
Keywords: Parkinson's, movement analysis, artificial intelligence, convolutional neural networks, drawing tasks, deep learning classifier, diagnosis
Journal or Publication Title: Neural Computing and Applications
Publisher: Springer-Verlag
ISSN: 0941-0643
DOI / ID Number: 10.1007/s00521-021-06469-7
Copyright Information:

Copyright The Author(s) 2021

Related URLs:
Item Statistics: View statistics for this item

Actions (login required)

Item Control Page Item Control Page